Hlb-CIFAR10 0.2.0: New world record (~<12.38s) on single-GPU CIFAR10

What it does

Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!) - Release beta v0.2.0 (~12.31-12.38s) · tysam-code/hlb-CIFAR10

New speed: ~12.31-12.38 seconds on an A100 SXM4 (through Colab). Many, many thanks to @99991 ( https://github.com/99991/cifar10-fast-simple ) for their help with finding the issues that eventually led to some of these improvements, as well as detailed debugging and verification of results on their end. I encourage you to check out some of their work! <3 :) -- Swap the memory channels out for channels_last (in beta for pytorch currently) -- Replace the nn.AdaptiveMaxPooling with a similarly-named class wrapping torch.amax (nearly a ~.5 second speedup in total) -- Replace GhostNorm with a more noisy BatchNorm to take advantage of the faster/simpler kernels. This resulted in roughly a 5.25…from github.com

In the maker’s words, at launch

Hello everyone, After recreating the accuracy&#x2F;rough speed from David Page's implementation in hlb-CIFAR10 0.1.0 (18.1s on an A100, SXM4, Colab), it was down to some basic NVIDIA kernel profiling to figure out which operations were the long poles in the tent. Perhaps (somewhat?) unsurprisingly, the NCHW <-> NHWC…

• 
  80% faster, 50% less memory, 0% loss of accuracy Llama finetuning2023 · github.com · ▲385

  Hi HN! I'm just sharing a project I've been working on during the LLM Efficiency Challenge - you can now finetune Llama with QLoRA 5x faster than Huggingface's original implementation on your own local GPU. Some highlights: 1. Manual autograd engine - hand derived backprop steps. 2. QLoRA &#x2F; LoRA 80% faster, 50% less memory. 3. All kernels written in OpenAI's Triton language. 4. 0% loss in accuracy - no approximation methods - all exact. 5. No change of hardware necessary. Supports NVIDIA GPUs since 2018+. CUDA 7.5+. 6. Flash Attention support via Xformers. 7. Supports 4bit and 16bit…

• 
  I've built a locally running Perplexity clone2024 · github.com · ▲669

  The video demo runs a 7b Model on a normal gaming GPU. I think it already works quite well (accounting for the limited hardware power). :)

• 
  Llama 3.1 70B on a single RTX 3090 via NVMe-to-GPU bypassing the CPUFeb 2026 · github.com · ▲395

  Hi everyone, I'm kinda involved in some retrogaming and with some experiments I ran into the following question: "It would be possible to run transformer models bypassing the cpu&#x2F;ram, connecting the gpu to the nvme?" This is the result of that question itself and some weekend vibecoding (it has the linked library repository in the readme as well), it seems to work, even on consumer gpus, it should work better on professional ones tho

• WM
  We made glhf.chat – run almost any open-source LLM, including 405B2024 · glhf.chat · ▲161

  Try it out! https:&#x2F;&#x2F;glhf.chat&#x2F; Hey HN! We’ve been working for the past few months on a website to let you easily run (almost) any open-source LLM on autoscaling GPU clusters. It’s free for now while we figure out how to price it, but we expect to be cheaper than most GPU offerings since we can run the models multi-tenant. Unlike Together AI, Fireworks, etc, we’ll run any model that the open-source vLLM project supports: we don’t have a hardcoded list. If you want a specific model or finetune, you don’t have to ask us for it: you can just paste the Hugging Face link in and…

• 
  Cuq – Formal Verification of Rust GPU Kernels2025 · github.com · ▲94

  A pipeline that translates Rust GPU code into formal Coq models, as a foundation for memory model proofs - neelsomani/vericuda

• 
  Running Gemma-4 26B at 124 tokens/SEC on a CPU, no GPUJun 2026 · apeg.dev · ▲10

  I wanted to know how fast a 26B mixture-of-experts model could run on a desktop CPU with no GPU. Got ~40 tok&#x2F;s single-stream (lossless) and ~124 batched. The surprising part was the byte budget: for this model you compress the output head (32% of per-token bytes), not the experts (16%). The writeup has the bandwidth roofline and the dead-ends; the repo has the reproducible recipe. Happy to answer questions. Repo: https:&#x2F;&#x2F;github.com&#x2F;arun-prasath2005&#x2F;gemma4-cpu-moe

• 
  SimCity, but with Permits▲936

  A free city-building game in your browser. You are the mayor. You know what the city needs. Now get it past the zoning board, the neighbors, the appeals court and the next election.

  Life & fun · 3d ago · permit.petercai.com

• IV
  I've been paying for a rural Tanzanian's education for 10 years▲778

  Life & fun · 15d ago · tanzaniaeducationproject.org

• 
  Bigwords.page – Turn any screen into a sign. The URL is the app▲728

  Turn a phone, tablet or TV into a sign. Type a message and it fills the screen: welcome signs, timers, Wi-Fi passwords and more. No app, no account, free.

  Life & fun · 16d ago · bigwords.page

• 
  Guitoro, a virtual guitar you strum with your keyboard▲573

  Play a free virtual guitar online with your keyboard or by touch. Slow songs down and see every chord, string and strum. Acoustic, classic, electric and bass.

  Life & fun · 10d ago · guitoro.com

• 
  See *almost* any carriers phone settings▲432

  Carrier settings from iPhone, Pixel and Galaxy firmware, decoded and compared: APNs, VoLTE, 5G and Wi-Fi Calling per carrier, and what each build changed.

  Life & fun · 14d ago · carrierexplode.com

• 
  The whole Solar System and every tracked satellite, live in the browser▲407

  Life & fun · 24d ago · space.bl2.net

• 
  New AI edits images based on text instructions▲1,098

  This works suprisingly well. Just give it instructions like "make it winter" or "remove the cars" and the photo is altered. Here are some examples of transformations it can make: Golden gate bridge: https:&#x2F;&#x2F;raw.githubusercontent.com&#x2F;brycedrennan&#x2F;imaginAIry&#x2F;ma... Girl with a pearl earring: https:&#x2F;&#x2F;raw.githubusercontent.com&#x2F;brycedrennan&#x2F;imaginAIry&#x2F;ma... I integrated this new InstructPix2Pix model into imaginAIry (python library) so it's easy to use for python developers.

  AI · 2023 · github.com

• 
  HyperSwitch▲715

  Fast, reliable, and affordable open source payments switch

  Dev tools · 2023 · hyperswitch.io

• 
  I've built a C# IDE, Runtime, and AppStore inside Excel▲670

  The project is called QueryStorm. It uses Roslyn to offer C# (and VB.NET) support in Excel, as an alternative to VBA. I've posted about it before, but a lot has changed since then so figured I'd share an update. The current version includes a host of new features, namely a C# debugger, support for NuGet packages, and the ability to publish Excel extensions to an "AppStore" (which is essentially a NuGet repository). The AppStore can be used by anyone with the (free) runtime component. Another great addition is the community license, which is a free license for individuals and small companies…

  Work · 2023 · querystorm.com

• 
  I'm a doctor and made a responsive breathing app for stress and anxiety▲666

  Hey HN! Some more info: I’m an NHS doctor and the founder of Pi-A (https:&#x2F;&#x2F;www.pi-a.io) which developed Lungy (https:&#x2F;&#x2F;www.lungy.app). Lungy is an app (iOS only for now) that responds to breathing in real-time and was designed to make breathing exercises more engaging and beneficial to do. It hopefully has many aspects of interest to the HN community – real-time fluid, cloth and soft body sims running on the phone’s GPU. My background is as a junior surgical trainee and I started building Lungy in 2020 during the first COVID lockdown in London. During COVID, there were…

  Life & fun · 2023 · lungy.app

• 
  Product Hunt Rewind 2022▲620

  Your 2022 on Product Hunt

  Life & fun · 2023

• 
  LaunchPedia▲616

  200+ handpicked tools to skyrocket your product launch

  Growth · 2023 · launchpedia.co